Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6514. Min Act: -0.0001

Data Index: 919539 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6537. Min Act: -0.0001

Data Index: 877060 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5944. Min Act: -0.0001

Data Index: 1076219 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6175. Min Act: -0.0001

Data Index: 789298 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5925. Min Act: -0.0001

Data Index: 226155 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6037. Min Act: -0.0001

Data Index: 643551 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6240. Min Act: -0.0001

Data Index: 326412 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6006. Min Act: -0.0001

Data Index: 63669 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5676. Min Act: -0.0001

Data Index: 183535 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5503. Min Act: -0.0001

Data Index: 587099 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5937. Min Act: -0.0001

Data Index: 991425 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5577. Min Act: -0.0001

Data Index: 938255 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5397. Min Act: -0.0001

Data Index: 435924 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5802. Min Act: -0.0001

Data Index: 436202 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1264503 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5875. Min Act: -0.0001

Data Index: 155036 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5285. Min Act: -0.0001

Data Index: 332522 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5565. Min Act: -0.0001

Data Index: 973578 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5873. Min Act: -0.0001

Data Index: 201402 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5531. Min Act: -0.0001

Data Index: 17701 (C4 (Web Text))

Max Activating Token Index: 627